Hey guys!

Hey guys!
When we index into a vector store with LlamaIndex (in this case a weaviate vector store)

Plain Text

vector_store = WeaviateVectorStore(
    weaviate_client=client, index_name="Wikiindex_docs"
)
storage_context = StorageContext.from_defaults(vector_store=vector_store)

doc_index = VectorStoreIndex.from_documents([], storage_context=storage_context)

for d in tqdm(docs_list):
    doc_index.insert(d)

Is it that this point that the embeddings are also stored in the Weviate base or are the embeddings computed at the runtime of a query?

5 comments

RRohan

yep, the embedding of the nodes are already computed at this point

SSriram Vadlamani

okay so then it's weird because when I query my weaviate client using postman, I get this:

Plain Text

                "text": "The fans voted in Jordan as an All-Star starter during his rookie season. Controversy arose before the 1985 NBA All-Star Game when word surfaced that seve....."
            },
            "vectorWeights": null

The vectorWeights field is null and I don't see the embeddings of this text anywhere

SSriram Vadlamani

or am I querying the database wrong?

RRohan

That's weird. Are you facing the same issue when querying through LlamaIndex?

Haven't used weaviate with postman before, hence not really sure if that's expected or not.

SSriram Vadlamani

actually I figured it out. I was indeed querying with a missing parameter.

Weaviate doesn't show the vector field by default, so I just had to specify the following in the URL:
http://localhost:8080/v1/objects?include=vector

And a GET method on that gives me the vector as well 🙂

Add a reply

Find answers from the community

Hey guys!